janitor

janitor
git clone https://git.prime8.dev/janitor.git
Log | Files | Refs | README | LICENSE

whisper-feature.h (2046B)

      1 /**
      2  * Copyright (c)  2023  Xiaomi Corporation (authors: Fangjun Kuang)
      3  *
      4  * See LICENSE for clarification regarding multiple authors
      5  *
      6  * Licensed under the Apache License, Version 2.0 (the "License");
      7  * you may not use this file except in compliance with the License.
      8  * You may obtain a copy of the License at
      9  *
     10  *     http://www.apache.org/licenses/LICENSE-2.0
     11  *
     12  * Unless required by applicable law or agreed to in writing, software
     13  * distributed under the License is distributed on an "AS IS" BASIS,
     14  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
     15  * See the License for the specific language governing permissions and
     16  * limitations under the License.
     17  */
     18 
     19 #ifndef KALDI_NATIVE_FBANK_CSRC_WHISPER_FEATURE_H_
     20 #define KALDI_NATIVE_FBANK_CSRC_WHISPER_FEATURE_H_
     21 
     22 #include <cstdint>
     23 #include <memory>
     24 #include <vector>
     25 
     26 #include "kaldi-native-fbank/csrc/feature-window.h"
     27 #include "kaldi-native-fbank/csrc/mel-computations.h"
     28 
     29 namespace knf {
     30 
     31 struct WhisperFeatureOptions {
     32   WhisperFeatureOptions(const FrameExtractionOptions &frame_opts = {},
     33                         int32_t dim = 80)
     34       : frame_opts(frame_opts), dim(dim) {}
     35 
     36   FrameExtractionOptions frame_opts;
     37   int32_t dim = 80;
     38 
     39   std::string ToString() const;
     40 };
     41 
     42 class WhisperFeatureComputer {
     43  public:
     44   // note: opts.frame_opts is ignored and we reset it inside
     45   explicit WhisperFeatureComputer(const WhisperFeatureOptions &opts = {});
     46 
     47   int32_t Dim() const { return opts_.dim; }
     48 
     49   const FrameExtractionOptions &GetFrameOptions() const {
     50     return opts_.frame_opts;
     51   }
     52 
     53   void Compute(float /*signal_raw_log_energy*/, float /*vtln_warp*/,
     54                std::vector<float> *signal_frame, float *feature);
     55 
     56   // if true, compute log_energy_pre_window but after dithering and dc removal
     57   bool NeedRawLogEnergy() const { return false; }
     58 
     59   using Options = WhisperFeatureOptions;
     60 
     61  private:
     62   std::unique_ptr<MelBanks> mel_banks_;
     63   WhisperFeatureOptions opts_;
     64 };
     65 
     66 }  // namespace knf
     67 
     68 #endif  // KALDI_NATIVE_FBANK_CSRC_WHISPER_FEATURE_H_